Machine Learning

Predicting Returns with Text Data

We introduce a new text-mining methodology that extracts sentiment information from news articles to predict asset returns.

Fixed Income

Active Fixed Income Illusions

Across a broad set of popular active fixed income categories, we find that passive exposures to traditional risk premia (especially exposure to credit risk) explain the majority of fixed income manager active returns.

Tax Aware

Lot Layering: The New Frontier for Hedge Fund Partnership Allocations

Despite its unavoidable deficiency caused by current regulations, we believe that lot layering aligns tax and economics more closely than any of the “aggregation” methods presently used by most hedge funds.

ESG Investing

Responsible Investing: The ESG-Efficient Frontier

Combining several large data sets, we compute the empirical ESG-efficient frontier and show the costs and benefits of responsible investing.

Market Risk and Efficiency

Economics with Market Liquidity Risk

We discuss the effects of market liquidity risk on asset pricing, investment management, corporate finance, banking, financial crises, macroeconomics, monetary policy, fiscal policy, and other economic areas.

Working Paper

Risk Parity Is Not Short Volatility (Not That There's Anything Wrong with Short Volatility)

Are risk parity strategies hiding an implicit short volatility? To find out, we simulated stylized versions of three asset-class (equity, fixed income, and commodities) risk parity and short volatility strategies, and we compared the trading behavior and returns of each.

Factor/Style Investing

How Do Factor Premia Vary Over Time? A Century of Evidence

We examine four prominent factor premia – value, momentum, carry, and defensive – over a century from six asset classes. The results offer support for time-varying risk premia models with important implications for theory seeking to explain the sources of factor returns.

Fixed Income

Looking Under the Hood of Active Credit Managers

We find that credit long/short managers tend to have high passive exposure to the credit risk premium. In contrast, we find that high-yield-focused long-only managers provide less exposure to the credit risk premium than their respective benchmarks.

Tax Aware

Should Taxable Investors Shun Dividends?

We evaluate the tax benefit of dividend avoidance for quantitative multi-style strategies and find that dividend avoidance generally reduces implementation efficiency, thus lowering expected pre-tax returns.

Machine Learning

Autoencoder Asset Pricing Models

We propose a new latent factor conditional asset pricing model, which delivers out-of-sample pricing errors that are far smaller (and generally insignificant) compared to other leading factor models.